Towards Ultra-Low Latency: Binarized Neural Network Architectures for In-Vehicle Network Intrusion Detection

TL;DR

This paper introduces a lightweight Binarized Neural Network-based intrusion detection system for in-vehicle networks, achieving real-time performance and high accuracy suitable for deployment on micro-controllers.

Contribution

It develops a novel BNN framework with hybrid binary encoding for non-payload features, optimized for real-time vehicle network intrusion detection.

Findings

Effective anomaly detection and traffic classification

Suitable for deployment on micro-controllers

Achieves real-time intrusion detection performance

Abstract

The Control Area Network (CAN) protocol is essential for in-vehicle communication, facilitating high-speed data exchange among Electronic Control Units (ECUs). However, its inherent design lacks robust security features, rendering vehicles susceptible to cyberattacks. While recent research has investigated machine learning and deep learning techniques to enhance network security, their practical applicability remains uncertain. This paper presents a lightweight intrusion detection technique based on Binarized Neural Networks (BNNs), which utilizes payload data, message IDs, and CAN message frequencies for effective intrusion detection. Additionally, we develop hybrid binary encoding techniques to integrate non-binary features, such as message IDs and frequencies. The proposed method, namely the BNN framework specifically optimized for in-vehicle intrusion detection combined with hybrid binary quantization techniques for non-payload attributes, demonstrates efficacy in both anomaly detection and multi-class network traffic classification. The system is well-suited for deployment on micro-controllers and Gateway ECUs, aligning with the real-time requirements of CAN bus safety applications.